metadata
library_name: transformers
license: apache-2.0
base_model: AnonymousCS/populism_multilingual_bert_cased_v2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: populism_classifier_150
results: []
populism_classifier_150
This model is a fine-tuned version of AnonymousCS/populism_multilingual_bert_cased_v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2842
- Accuracy: 0.8737
- 1-f1: 0.6377
- 1-recall: 0.88
- 1-precision: 0.5
- Balanced Acc: 0.8764
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
|---|---|---|---|---|---|---|---|---|
| 0.3228 | 1.0 | 7 | 0.2659 | 0.8586 | 0.6216 | 0.92 | 0.4694 | 0.8849 |
| 0.1422 | 2.0 | 14 | 0.4452 | 0.8788 | 0.5862 | 0.68 | 0.5152 | 0.7938 |
| 0.1568 | 3.0 | 21 | 0.2842 | 0.8737 | 0.6377 | 0.88 | 0.5 | 0.8764 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3